{"id":1810,"date":"2014-08-19T07:41:11","date_gmt":"2014-08-18T23:41:11","guid":{"rendered":"http:\/\/hwind.me\/?p=1810"},"modified":"2014-08-19T07:44:02","modified_gmt":"2014-08-18T23:44:02","slug":"%e5%a4%a7%e6%95%b0%e6%8d%ae%e7%9a%84%e5%ba%94%e7%94%a8","status":"publish","type":"post","link":"https:\/\/hwind.me\/?p=1810","title":{"rendered":"\u5927\u6570\u636e\u7684\u5e94\u7528"},"content":{"rendered":"<p>\u4eca\u5929\u6211\u4eec\u6765\u804a\u4e00\u4e0b\uff0c\u5982\u679c\u4f60\/\u67d0\u4f01\u4e1a\u5df2\u7ecf\u6709\u4e86\u5927\u6570\u636e\u7684\u786c\u4ef6\u5e73\u53f0\uff0c\u90a3\u4e48\u5230\u5e95\u80fd\u7528\u5b83\u6765\u505a\u4ec0\u4e48\u5462\uff1f\n<\/p>\n<p><a href=\"http:\/\/people.ischool.berkeley.edu\/~hal\/Papers\/2013\/BeyondBigDataPaperFINAL.pdf\">http:\/\/people.ischool.berkeley.edu\/~hal\/Papers\/2013\/BeyondBigDataPaperFINAL.pdf<\/a> \u8fd9\u7bc7\u6765\u81eaGoogle\u9996\u5e2d\u7ecf\u6d4e\u5b66\u5bb6\u7684\u8bba\u6587\u5bf9\u8fd9\u4e2a\u95ee\u9898\u6709\u7b80\u6d01\u660e\u4e86\u7684\u9610\u8ff0\uff1a\n<\/p>\n<ol>\n<li>\u6570\u636e\u7684\u62bd\u53d6\u548c\u5206\u6790\n<\/li>\n<li>\u79c1\u4eba\u5316\/\u5ba2\u6237\u5316\u5b9a\u5236\n<\/li>\n<li>\u8fde\u7eed\u4e0d\u65ad\u7684\u5b9e\u9a8c\n<\/li>\n<li>\u57fa\u4e8e\u66f4\u597d\u7684\u76d1\u6d4b\u800c\u63d0\u4f9b\u65b0\u578b\u7684\u670d\u52a1\u5957\u9910\/\u5408\u7ea6\n<\/li>\n<\/ol>\n<p>\u76f4\u63a5\u7ffb\u8bd1\u8fc7\u6765\u6709\u70b9\u62d7\u53e3\uff0c\u4e0d\u8fc7\u5177\u4f53\u7684\u4f8b\u5b50\u5c31\u5f88\u597d\u7406\u89e3\u4e86\u3002\u4eca\u5929\u5148\u8bf4\u6570\u636e\u7684\u62bd\u53d6\u548c\u5206\u6790\uff0c\u51e0\u4e4e\u6bcf\u4e2a\u8c08\u5230\u5927\u6570\u636e\u7684\u4eba\u90fd\u4f1a\u8c08\u5230\u8fd9\u4e00\u70b9\uff0c\u8fd9\u662f\u5176\u6700\u76f4\u63a5\u800c\u666e\u904d\u7684\u5e94\u7528\u3002\n<\/p>\n<p>\u6bd4\u5982\u4f60\u63d0\u4f9b\u4e86\u4e00\u4e2a\u7f51\u7edc\u670d\u52a1\uff0c\u4f60\u5f88\u60f3\u77e5\u9053\u8fd9\u4e2a\u670d\u52a1\u7684\u8fd0\u884c\u548c\u4f7f\u7528\u60c5\u51b5\uff0c\u90a3\u4e48\u600e\u4e48\u529e\u5462\uff1f\u5f88\u7b80\u5355\uff0c\u8bb0Log(\u65e5\u5fd7)\u5c31\u662f\u4e86:&#8221;\u51e0\u70b9\u51e0\u5206\uff0c\u8c01\uff0c\u6765\u81ea\u54ea\u4e2aIP\uff0c\u8bbf\u95ee\u4e86\u54ea\u4e2a\u670d\u52a1\uff0c\u6210\u529f\u8fd8\u662f\u5931\u8d25&#8221;\u3002\u65e9\u4e9b\u5e74Log\u4e00\u529e\u5c31\u7528\u6765\u76d1\u6d4b\u7cfb\u7edf\u8fd0\u884c\u662f\u4e0d\u662f\u6b63\u5e38\uff0c\u901a\u5e38\u7cfb\u7edf\u7ba1\u7406\u5458\u5199\u4e00\u4e9bPerl\u811a\u6b65\u626b\u63cf\u4e00\u4e0b\u5c31\u5b8c\u4e8b\u513f\u4e86\u3002\u4e5f\u6709\u4eba\u5e72\u8106\u628aLog\u5199\u8fdb\u6570\u636e\u5e93\uff0c\u8fd9\u6837\u7528SQL\u8bed\u53e5\u5c31\u53ef\u4ee5\u67e5\u8be2\uff0c\u975e\u5e38\u65b9\u4fbf\u3002 \u9898\u5916\u8bdd\uff1a\u7a81\u7136\u60f3\u8d77\u6765\u4e4b\u524d\u78b0\u5230\u7684\u4e00\u4e2a\u9879\u76ee\uff0cLog\u5168\u90e8\u8bb0\u5230\u6570\u636e\u5e93\uff0c\u540e\u6765\u6bcf\u5929\u6d77\u91cf\u7684SQL\u8bed\u53e5\u63d2\u5165\uff0c\u67e5\u8be2\uff0c\u7ec8\u4e8e\u625b\u4e0d\u4f4f\u4e86\u3002\n<\/p>\n<p>\u540e\u6765\u51fa\u73b0\u4e86Hadoop\u8fd9\u79cd\u7684\u5206\u5e03\u5f0f\u7cfb\u7edf\uff0c\u4e4b\u524d\u505a\u4e0d\u5230\u7684\u4e8b\u60c5\u53ef\u4ee5\u505a\u4e86: \u516c\u53f8\u7684\u8001\u677f\u60f3\u77e5\u9053\u4ea7\u54c1\u7684\u4f7f\u7528\u72b6\u51b5\uff1b\u4ea7\u54c1\u7ecf\u7406\u60f3\u77e5\u9053\u67d0\u4e2a\u65b0\u529f\u80fd\u662f\u5426\u53d7\u6b22\u8fce\uff1b\u5e02\u573a\u8425\u9500\u4eba\u5458\u60f3\u77e5\u9053\u5230\u5e95\u8c01\u624d\u662f\u76ee\u6807\u5ba2\u6237\uff1b\u7cfb\u7edf\u7ef4\u62a4\u4eba\u5458\u60f3\u77e5\u9053\u670d\u52a1\u5668\u8d1f\u8f7d\u3002\n<\/p>\n<p>\u8fd9\u79cd\u7cfb\u7edf\u4e00\u822c\u7684\u7ed3\u6784\u5982\u4e0b\uff1a\n<\/p>\n<ul>\n<li>\u9996\u5148\u628aLog\u96c6\u4e2d\u5230HDFS\u6587\u4ef6\u7cfb\u7edf\uff0c\u7136\u540e\u7528Hadoop Cluster\u8bbf\u95eeHDFS\u3002\n<\/li>\n<li>\u5177\u4f53\u7684\u67e5\u8be2\u8bed\u53e5\u7531\u7528\u6237\u5411Hadoop Cluster\u63d0\u4f9b:\u7528\u6237\u65e2\u53ef\u4ee5\u5199MapReduce Job\u6765\u544a\u8bc9Hadoop Cluster\u8981\u600e\u4e48\u5904\u7406\u65e5\u5fd7\uff0c\u4e5f\u53ef\u4ee5\u76f4\u63a5\u5199Hive script. Hive\u662f\u4e00\u79cd\u8bed\u6cd5\u5f88SQL\u975e\u5e38\u50cf\u7684\u8bed\u8a00\uff0c\u5b83\u9996\u5148\u8d4b\u4e88Log\u4ee5\u7ed3\u6784\u5316\u7684\u5b9a\u4e49\uff0c\u7136\u540e\u50cfSQL\u8bed\u53e5\u4e00\u6837\u505a\u67e5\u8be2\u3002\n<\/li>\n<li>Hadoop\u8fd0\u7b97\u7684\u7ed3\u679c\u901a\u5e38\u4f1a\u5b58\u50a8\u5230\u6570\u636e\u5e93\u91cc\u3002\u56e0\u4e3a\u8fd0\u7b97\u7ed3\u679c\u5df2\u7ecf\u662f\u5904\u7406\u8fc7\u7684\u6570\u636e\uff0c\u6570\u636e\u91cf\u4e0d\u5927\uff0c\u5b58\u50a8\u5230\u6570\u636e\u5e93\u65b9\u4fbf\u4e4b\u540e\u5feb\u901f\u67e5\u8be2\uff0c\u5e76\u4e14\u53ef\u4ee5\u548c\u5f88\u591a\u73b0\u6709\u7684\u57fa\u4e8e\u6570\u636e\u5e93\u7684\u5e94\u7528\u7ed3\u5408\u3002\n<\/li>\n<li>\u6700\u540e\u65e0\u8bba\u662f\u8001\u677f\u7684\uff0c\u4ea7\u54c1\u7ecf\u7406\u7684\uff0c\u5e02\u573a\u8425\u9500\u4eba\u5458\u7684\uff0c\u8fd8\u662f\u7cfb\u7edf\u7ef4\u62a4\u4eba\u5458\u7684\u95ee\u9898\uff0c\u90fd\u53ef\u4ee5\u901a\u8fc7\u4ece\u6570\u636e\u5e93\u751f\u6210\u7684\u62a5\u8868\u6765\u56de\u7b54\u3002\u6700\u7b80\u5355\u7684\u6bd4\u5982\u7528Excel\u8fde\u63a5\u5230\u6570\u636e\u5e93\u5c31\u53ef\u4ee5\u505a\u62a5\u8868\uff0c\u590d\u6742\u7684\u5f53\u7136\u6709\u5404\u79cd\u5404\u6837\u7684\u62a5\u8868\u4ea7\u54c1\u3002\n<\/li>\n<\/ul>\n<p><img decoding=\"async\" src=\"http:\/\/hwind.me\/wp-content\/uploads\/2014\/08\/HadoopArch.png\" alt=\"\"\/>\n\t<\/p>\n<p>\u5728\u4e91\u8ba1\u7b97\u5e73\u53f0\u9010\u6e10\u53d1\u8fbe\u7684\u4eca\u5929\uff0c\u5f88\u5feb\u5c31\u53ef\u4ee5\u641e\u51fa\u8fd9\u6837\u7684\u7cfb\u7edf\u3002\u5373\u4f7f\u4e0d\u7528\u4e91\u8ba1\u7b97\u5e73\u53f0\uff0c\u7167\u7740\u6587\u6863\u642d\u4e2aHadoop\u51fa\u6765\uff0c\u7136\u540e\u90e8\u7f72\u8fd9\u6837\u7684\u7cfb\u7edf\u4e5f\u5e76\u975e\u96be\u4e8b\u3002\u5927\u6570\u636e\u4ece\u6b64\u4e0d\u518d\u662f\u4ec0\u4e48\u795e\u79d8\u7684\uff0c\u53ea\u6709\u5c11\u6570\u51e0\u5bb6\u5927\u516c\u53f8\u624d\u73a9\u513f\u7684\u4e86\u7684\u4e8b\u60c5\u3002\n<\/p>\n<p>\u53ef\u662f\u5982\u679c\u5927\u6570\u636e\u4e4b\u505a\u5230\u8fd9\u4e2a\u7a0b\u5ea6\uff0c\u90a3\u5c31\u592a\u521d\u7ea7\u4e86\u3002\u5f88\u591a\u5730\u65b9\u5728\u804a\u5927\u6570\u636e\uff0c\u6700\u540e\u65e0\u975e\u662f\u5728\u6d77\u91cf\u6570\u636e\u4e0a\u8ba1\u7b97\u4e00\u4e2a\u5e73\u5747\u503cAVG,\u6700\u5927\u503c\u6700\u5c0f\u503cMAX,MIN\uff1b\u6216\u8005\u6309\u67d0\u4e9b\u4e1c\u897f\u5206\u5206\u7c7bGroupBy\uff1b\u518d\u6216\u8005\u628a\u4e24\u7ec4\u6570\u636e\u5173\u8054\u4e00\u4e0bJoin\u3002\u8fd9\u51e0\u4e2a\u51fd\u6570\u53ef\u662f\u521d\u4e2d\u751f\u5c31\u4f1a\u7684\u3002\u3002\u3002\u6240\u4ee5\u5728\u5927\u6570\u636e\u5f88\u70ed\u7684\u4eca\u5929\uff0c\u673a\u5668\u5b66\u4e60\u4eba\u5de5\u667a\u80fd\u4e5f\u5f88\u70ed\u3002\u4e00\u76f4\u6ca1\u6709\u52c7\u6c14\u53bb\u6df1\u5165\u7814\u7a76\u4e00\u4e0b\u673a\u5668\u5b66\u4e60\u4eba\u5de5\u667a\u80fd\u7684\u7406\u8bba\uff0c\u6240\u6709\u7684\u77e5\u8bc6\u8fd8\u505c\u7559\u5728\u8bfb\u4e66\u65f6\u5019\u8bfb\u7684\u4e00\u70b9\u6750\u6599\u3002\u4e0d\u8fc7\u6211\u76f8\u4fe1\u53ea\u6709\u5728\u5927\u6570\u636e\u96c6\u4e0a\u8fd0\u7528\u7edf\u8ba1\u5b66\u7684\u65b9\u6cd5\u624d\u80fd\u5f97\u5230\u66f4\u591a\u6709\u610f\u601d\u7684\u7ed3\u679c\u3002\n<\/p>\n<p>\u73b0\u5728\u5df2\u7ecf\u6709\u8d8a\u6765\u8d8a\u591a\u7684\u5927\u516c\u53f8\u5c0f\u516c\u53f8\u6b63\u5728\u628a\u673a\u5668\u5b66\u4e60\u4eba\u5de5\u667a\u80fd\u7684\u7b97\u6cd5\u642c\u5230cloud\u4e0a\u6765\uff0c\u6211\u89c9\u5f97\u8fd9\u662f\u4e2a\u4e0d\u9519\u7684\u65b9\u5411\u3002\u5982\u4eca\u8fd9\u4e9b\u7b97\u6cd5\u7684\u95e8\u69db\u592a\u9ad8\u4e86\uff0c \u4e00\u822c\u7684\u7a0b\u5e8f\u5458\u90fd\u4e0d\u592a\u6e05\u695a\uff0c\u66f4\u8c08\u4e0d\u4e0a\u5e94\u7528\u4e86\u3002\u6574\u4e2aIT\u4ea7\u4e1a\u7684\u5386\u53f2\u90fd\u662f\u4e0d\u65ad\u628a\u5404\u79cd\u6280\u672f\u5c01\u88c5\u62bd\u8c61\u5230\u4e0d\u540c\u7684\u5c42\u6b21\u6a21\u5757\uff0c\u5e0c\u671b\u673a\u5668\u5b66\u4e60\u4eba\u5de5\u667a\u80fd\u7684\u6700\u65b0\u6210\u679c\u5feb\u70b9\u88ab\u6a21\u5757\u5316\u3002\n<\/p>\n<p>\n\u00a0<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4eca\u5929\u6211\u4eec\u6765\u804a\u4e00\u4e0b\uff0c\u5982\u679c\u4f60\/\u67d0\u4f01\u4e1a\u5df2\u7ecf\u6709\u4e86\u5927\u6570\u636e\u7684\u786c\u4ef6\u5e73\u53f0\uff0c\u90a3\u4e48\u5230\u5e95\u80fd\u7528\u5b83\u6765\u505a\u4ec0\u4e48\u5462\uff1f http:\/\/peopl [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"enabled":false},"version":2}},"categories":[9],"tags":[84],"class_list":["post-1810","post","type-post","status-publish","format-standard","hentry","category-it","tag-bigdata"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p4T8yD-tc","_links":{"self":[{"href":"https:\/\/hwind.me\/index.php?rest_route=\/wp\/v2\/posts\/1810","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hwind.me\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hwind.me\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hwind.me\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/hwind.me\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1810"}],"version-history":[{"count":3,"href":"https:\/\/hwind.me\/index.php?rest_route=\/wp\/v2\/posts\/1810\/revisions"}],"predecessor-version":[{"id":1814,"href":"https:\/\/hwind.me\/index.php?rest_route=\/wp\/v2\/posts\/1810\/revisions\/1814"}],"wp:attachment":[{"href":"https:\/\/hwind.me\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1810"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hwind.me\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1810"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hwind.me\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1810"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}